Real-time adaptive algorithms using a Graphics Processing Units

Abstract

[EN] Graphics Processing Units (GPUs) have been recently used as coprocessors capable of performing tasks that are not necessarily related to graphics processing in order to optimize computing resources. The use of GPUs has being extended to a wide variety of intensive-computation applications among which audio processing is included. However data transactions between the CPU and the GPU and vice versa have questioned the viability of GPUs for applications in which direct and real-time interaction between microphone and loudspeaker is required. One of the audio applications that requires real-time feedback is adaptive channel identification. Particularly, when the partitioned Least Mean Squares (LMS) algorithm is used in the frequency domain, the size of input-data buffers and filters and how they can be managed in order to successfully exploit the GPU resources is an important key in the design process. This paper discusses the design and implementation of all the processing blocks of an adaptive channel identification system on a GPU, proposing a GPU implementation that can be easily adapted to any acoustic scenario, while freeing up CPU resources for other tasks.